NASA scientists use machine-learning to predict hurricane intensity

Predicting whether a hurricane will increase in intensity is extremely difficult because it depends on the surrounding environment as well as what’s happening inside these storms, but the scientists at NASA have made it possible.

NASA scientists use machine-learning to predict hurricane intensity
NASA scientists use machine-learning to predict hurricane intensity

NASA scientists use machine-learning to predict hurricane intensity

Researches led by scientists at NASA’s reaction propulsion Laboratory in Southern California have used machine learning to develop an experimental computer model that promises to greatly improve the accuracy of detecting rapid-intensification events (hurricanes).

Hui Su, an atmospheric scientist at JPL said that it’s an important forecast to get right because of the potential for harm to people and property. Predicting whether a hurricane will increase in intensity is extremely difficult because it depends on the surrounding environment as well as what’s happening inside these storms, but the scientists at NASA have made it possible.

After sifting through years of satellite data, Su and her colleagues found that an honest indicator of how a hurricane’s strength will change over the subsequent 24 hours is the rainfall rate inside the storm’s inner core – the area within a 62-mile (100-kilometer) radius of the eyewall, or the dense wall of thunderstorms surrounding the eye.

The harder it’s raining inside a hurricane, the more likely the storm is to intensify. Researchers also found that changes in storm intensity depended on the ice water content of clouds within a hurricane. Outflow temperature which is the temperature of the air flowing away from the eye at the top of hurricanes also factored into intensity changes.

Su and her colleagues, including collaborators at the National Hurricane Center, are testing their model on storms during the present hurricane season to measure its performance. In the future, they decide to sift through satellite data to seek out additional hurricane characteristics that would improve their machine learning model.

Predictors like whether it’s raining harder in one a part of a hurricane versus another could give scientists a far better prediction on how the storm’s intensity might change over time.